stack/packages/mosaic/framework/tools/git/verify-clean-clone.sh

#!/usr/bin/env bash
# verify-clean-clone.sh -- prove the COMMITTED artifact runs, from a clean clone.
#
# ================== THIS FILE IS THE SECOND VERSION. THE FIRST HAD B1. ========
# B1 was: the delivered scripts were committed mode 100644, so the artifact
# returned 126 Permission denied for anyone who cloned it. Two of us ran 32/32
# because our local working copies had the exec bit set by hand at creation.
#
# I wrote v1 of this file to prevent exactly that. V1 COPIED THE WORKING-TREE
# FILES INTO A SCRATCH REPOSITORY AND ASSERTED THE SCRATCH REPOSITORY'S INDEX.
# cp preserves the local exec bit, so `git add` in the scratch repo recorded
# 100755 NO MATTER WHAT THE REAL REPOSITORY STORED. Reviewer reproduction:
#     git update-index --chmod=-x push-guard.sh test-push-guard.sh
#     ./verify-clean-clone.sh   ->  EXIT 0, "CLEAN CLONE: suite ran and passed"
# while the real index read 100644 -- the precise contaminated state B1 was.
#
#   THE CONTROL FOR THE DEFECT INHERITED THE DEFECT, BECAUSE IT MEASURED A COPY
#   INSTEAD OF THE SUBJECT. cp LAUNDERS MODE.
#
# Both of v1's mechanisms were right -- assert the INDEX not the disk, execute
# DIRECTLY not via `bash script`. They were applied to the wrong repository.
# So v2 changes what is measured, not how:
#   * mode is read from the SOURCE repository's COMMITTED TREE (git ls-tree),
#     which no local chmod can influence;
#   * the tree under test is produced by CLONING THAT COMMIT, so every mode
#     comes out of the object store rather than off my filesystem.
# There is no cp anywhere in this file, and that is deliberate.
#
# It also REFUSES rather than passes when the artifacts are untracked: an
# artifact that is not committed has no mode to verify, and a verifier that
# silently succeeds on nothing is the vacuous-absence failure all over again.

set -euo pipefail

readonly EX_FAIL=1
readonly EX_USAGE=64

REPO=""
REV="HEAD"

die() { printf 'usage error: %s\n' "$1" >&2; exit "$EX_USAGE"; }

while (( $# )); do
    case "$1" in
        --repo) REPO="${2:-}"; shift 2 ;;
        --rev)  REV="${2:-}";  shift 2 ;;
        *) die "unknown argument: $1" ;;
    esac
done

HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
[[ -n "$REPO" ]] || REPO="$HERE"

ARTIFACTS=(push-guard.sh test-push-guard.sh verify-clean-clone.sh mutate-push-guard.sh
           test-mutate-push-guard.sh
           test-verify-clean-clone.sh)
SUITE="test-push-guard.sh"

# --- the subject must be a real repository, or there is nothing to verify -----
if ! ROOT="$(git -C "$REPO" rev-parse --show-toplevel 2>/dev/null)"; then
    printf 'REFUSING: %s is not inside a git repository.\n' "$REPO" >&2
    printf 'This verifier checks the COMMITTED mode of the artifact. An uncommitted\n' >&2
    printf 'artifact has no committed mode, and passing here would prove nothing.\n' >&2
    exit "$EX_FAIL"
fi
if ! REV_SHA="$(git -C "$ROOT" rev-parse --verify --quiet "${REV}^{commit}")"; then
    printf 'REFUSING: %s does not resolve to a commit in %s\n' "$REV" "$ROOT" >&2
    exit "$EX_FAIL"
fi

# --- THE ARTIFACT'S COMMITTED PATH, NOT ITS BASENAME -------------------------
# v2 asserted `git ls-tree HEAD -- push-guard.sh`, which is a ROOT-RELATIVE
# pathspec. These files really live several directories down. Run in place and
# every artifact came back "NOT TRACKED" -- the verifier built to stop packaging
# false-greens could not verify the tree that ships it.
#
# The tests missed it because EVERY FIXTURE INSTALLED THE ARTIFACTS AT THE
# FIXTURE ROOT. 6/6 green proved flat-layout operation and nothing about the
# deployed path. THAT IS THE THIRD TIME ON THIS TOOL THAT A CONTROL VALIDATED A
# MODEL INSTEAD OF THE SUBJECT: v1 measured a cp'd scratch repo, and then v2's
# own tests measured a layout that does not exist. A fixture is a claim about
# the world, and an untested fixture is an unreviewed one.
#
# --show-prefix answers "where is this directory inside its repository", so the
# same prefix drives ls-tree, the cloned stat, and the suite's working dir.
PREFIX="$(git -C "$REPO" rev-parse --show-prefix)"

printf '=== subject ===\n'
printf '  repo   %s\n  rev    %s (%s)\n  prefix %s\n\n' \
    "$ROOT" "$REV" "$REV_SHA" "${PREFIX:-<repository root>}"

# --- 1. MODE, FROM THE COMMITTED TREE OF THE SUBJECT -------------------------
# git ls-tree reports what the COMMIT records. Nothing on my filesystem can
# move this number -- which is the whole point, and what v1 got wrong.
printf '=== committed modes (git ls-tree %s) ===\n' "$REV"
rc=0
for f in "${ARTIFACTS[@]}"; do
    entry="$(git -C "$ROOT" ls-tree "$REV_SHA" -- "${PREFIX}${f}")"
    if [[ -z "$entry" ]]; then
        printf '  FAIL  %s is NOT TRACKED at %s -- nothing committed to verify\n' "$f" "$REV"
        rc=1; continue
    fi
    mode="${entry%% *}"; rest="${entry#* }"; type="${rest%% *}"
    if [[ "$type" != blob ]]; then
        printf '  FAIL  %s is a %s at %s, not a regular file\n' "$f" "$type" "$REV"
        rc=1; continue
    fi
    case "$mode" in
        100755) printf '  ok    %s committed %s\n' "$f" "$mode" ;;
        120000) printf '  FAIL  %s is a SYMLINK (%s) -- the reviewed blob is a path, not the code\n' "$f" "$mode"; rc=1 ;;
        *)      printf '  FAIL  %s committed %s, needs 100755\n' "$f" "$mode"
                printf '        fix with: git update-index --chmod=+x %s && commit\n' "$f"
                rc=1 ;;
    esac
done
if (( rc != 0 )); then
    printf '\nREFUSING TO CONTINUE: the COMMITTED modes are wrong, whatever the disk says.\n'
    printf 'A clone of this commit would exit 126 for the next person.\n'
    exit "$EX_FAIL"
fi

# --- 2. RUN FROM A CLONE OF THAT COMMIT --------------------------------------
# Cloning materialises every file from the object store, so the modes on disk
# are the COMMITTED modes by construction. No cp, no local state, nothing this
# machine can contribute.
WORK="$(mktemp -d)"
trap 'rm -rf "$WORK"' EXIT

printf '\n=== cloning %s (no local mode bits survive this) ===\n' "$REV_SHA"
git clone -q --no-local --no-hardlinks "$ROOT" "$WORK/clone"
git -C "$WORK/clone" -c advice.detachedHead=false checkout -q "$REV_SHA"

for f in "${ARTIFACTS[@]}"; do
    printf '  clone disk mode: %s %s\n' "$(stat -c '%a' "$WORK/clone/${PREFIX}${f}")" "${PREFIX}${f}"
done

printf '\n=== executing DIRECTLY (./%s), not via "bash %s" ===\n' "$SUITE" "$SUITE"
# Invoking the interpreter explicitly masks a missing exec bit completely -- it
# is how the original green was obtained. Direct execution is the thing under
# test, so the mode has to be real for this line to succeed.
cd "$WORK/clone/${PREFIX}"
if ! "./$SUITE"; then
    printf '\nCLEAN-CLONE RUN FAILED.\n'
    exit "$EX_FAIL"
fi

printf '\n=== CLEAN CLONE: the COMMITTED artifact ran and passed ===\n'